Autoassociative-heteroassociative neural networks

被引：3
|
作者：
Kropas-Hughes, CV
Oxley, ME
Rogers, SK
Kabrisky, M
机构：
[1] USAF, Res Lab, Mat & Mfg Directorate, AFRL MLLP, Wright Patterson AFB, OH 45433 USA
[2] USAF, Inst Technol, Dept Math & Stat, Wright Patterson AFB, OH 45433 USA
[3] Qualia Comp Inc, Beavercreek, OH 45431 USA
[4] USAF, Inst Technol, Dept Elect & Comp Engn, Wright Patterson AFB, OH 45433 USA
来源：
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE | 2000年 / 13卷 / 05期
基金：
美国国家卫生研究院;
关键词：
neural networks; autoassociative neural networks; stability;
D O I：
10.1016/S0952-1976(00)00040-3
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
The Autoassociative-Heteroassociative Neural Network (A-HNN) is a unique integration of autoassociative and heteroassociative neural network mappings to provide a functional approximation of two variables from one. This new architecture provides three features: the autoassociative mapping enables a stability metric for assessing the robustness or accuracy of the heteroassociative mapping; the A-HNN generates the inverse of the encoding portion of an associated autoassociative neural network (AANN); and, empirically, the use of input data as target vectors (the autoassociative mapping) improves training performance of the network. Published by Elsevier Science Ltd.
引用
收藏
页码：603 / 609
页数：7
相关论文
共 50 条
  • [41] Robust stability for uncertain impulsive autoassociative-neural networks
    Qian, TH
    Guan, ZH
    Chen, GR
    DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES B-APPLICATIONS & ALGORITHMS, 2003, 10 (1-3): : 69 - 79
  • [42] FEATURE REDUCTION OF HYPERSPECTRAL DATA USING AUTOASSOCIATIVE NEURAL NETWORKS ALGORITHMS
    Licciardi, G.
    Del Frate, F.
    Duca, R.
    2009 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-5, 2009, : 176 - +
  • [43] Measurement Correction for Multiple Sensors Using Modified Autoassociative Neural Networks
    Sanchez, Javier Reyes
    Vellasco, Marley
    Tanscheit, Ricardo
    ENGINEERING APPLICATIONS OF NEURAL NETWORKS, 2012, 311 : 135 - 144
  • [44] DYNAMIC HETEROASSOCIATIVE NEURAL MEMORIES
    HASSOUN, MH
    NEURAL NETWORKS, 1989, 2 (04) : 275 - 287
  • [45] DIMENSIONALITY REDUCTION OF HYPERSPECTRAL DATA: ASSESSING THE PERFORMANCE OF AUTOASSOCIATIVE NEURAL NETWORKS
    Licciardi, G.
    Del Frate, F.
    Schiavon, G.
    Solimini, D.
    2010 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2010, : 4377 - 4380
  • [46] Principal component analysis of fuzzy data using autoassociative neural networks
    Denoeux, T
    Masson, MH
    IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2004, 12 (03) : 336 - 349
  • [47] Augmented Efficient BackProp for Backpropagation Learning in Deep Autoassociative Neural Networks
    Embrechts, Mark J.
    Hargis, Blake J.
    Linton, Jonathan D.
    2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010, 2010,
  • [48] Deep autoassociative networks
    Hand, C
    IC-AI'2001: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOLS I-III, 2001, : 1310 - 1315
  • [49] Diagnosing Faults in Power Transformers With Autoassociative Neural Networks and Mean Shift
    Miranda, Vladimiro
    Garcez Castro, Adriana R.
    Lima, Shigeaki
    IEEE TRANSACTIONS ON POWER DELIVERY, 2012, 27 (03) : 1350 - 1357
  • [50] Manipulation of attractors in feed-forward autoassociative neural networks for robust learning
    Amini, Nima
    Seyyedsalehi, Seyyed Ali
    2017 25TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2017, : 29 - 33
12345